The Reproducibility Crisis and R Scripts

The reproducibility crisis

One of the key features of scientific research is that results should be reproducible. This is also true for the statistical analyses that these results are based on. Unfortunately, over the last decade, we’ve discovered that a large portion of the research is not reproducible. The causes of this reproducibility crisis are complex. If we improve how we approach statistical analyses, then we can improve their reproducibility. Point and click statistical software is certainly useful, but it’s almost impossible to repeatedly produce the same exact sequence of clicks. We need a computer program to do that, which is exactly what we get if we save a copy of our code as an R script. Scripting is a huge advance over point-and-click, but we can go further and use the R Markdown package to produce ‘analysis notebooks’ to better record and explain what we have done and why.